The depletion of natural resources and the intermittence of renewable energy resources have pressed the need for a hybrid microgrid, combining the benefits of both AC and DC microgrids, minimizing the overall deficiency shortcomings and increasing the reliability of the system. The hybrid microgrid also supports the decentralized grid control structure, aligning with the current scattered and concentrated load scenarios. Hence, there is an increasing need to explore and reveal the integration, optimization, and control strategies regarding the hybrid microgrid. A comprehensive study of hybrid microgrid’s performance parameters, efficiency, reliability, security, design flexibility, and cost-effectiveness is required. This paper discusses major issues regarding the hybrid microgrids, the integration of AC and DC microgrids, their security and reliability, the optimization of power generation and load management in different scenarios, the efficient management regarding uncertainty for renewable energy resources, the optimal placement of feeders, and the cost-effective control methodologies for the hybrid microgrid. The major research areas are briefly explained, aiming to find the research gap that can further improve the performance of the grid. In light of the recent trends in research, novel strategies are proposed that are found most effective and cost-friendly regarding the hybrid microgrid. This paper will serve as a baseline for future research, comparative analysis, and further development of novel techniques regarding hybrid microgrids.

Energy shortage and environmental pollution issues can be reduced considerably with the development and usage of electric vehicles (EVs). However, electric vehicle performance and battery lifespan depend on a suitable battery arrangement to meet the various battery performance demands. The safety, reliability, and efficiency of EVs largely depends on the constant monitoring of the batteries and management of battery packs. This work comprehensively reviews different aspects of battery management systems (BMS), i.e., architecture, functions, requirements, topologies, fundamentals of battery modeling, different battery models, issues/challenges, recommendations, and active and passive cell balancing approaches, etc., as compared to the existing works which normally discuss one or two aspects only. The work describes BMS functions, battery models and their comparisons in detail for an efficient operation of the battery pack. Similarly, the work presents a comprehensive overview of issues and challenges faced by BMS and also provides recommendations to address these challenges. Cell balancing is very important for the battery performance and in this work various cell balancing methodologies and their comparisons are also presented in detail. Modeling of a cell balancer is presented and a comparative study is also carried out for active and passive cell balance technique in MATLAB/Simulink with an eight cell battery packcell balancing approach. The result shows that the active cell balancing technique is more advantageous than passive balancing for electrical vehicles using lithium-ion batteries.

A number of modern metaheuristic optimization techniques are being exploited to work out a single-objective economic dispatch (ED) problem. The dispatch problems even become more complicated and complex when they consider operational and system constraints, such as network transmission losses, valve-point loading effects originating due to sequential opening of a number of steam admission valves to meet the ever-increasing demand, ramp rate limits, prohibited operating zones, multiple fuel options, spinning reserve, and so on. The heavy constraints make the otherwise convex linear smooth dispatch problem as highly nonconvex nonlinear nonsmooth one. Finding optimal solution for such kind of a constrained nonlinear problem through the deterministic numerical and convex characteristics-based optimization techniques is a difficult task to accomplish. Researchers have frequently employed one of the metaheuristic optimization techniques with powerful computational ability named particle swarm optimization (PSO) to deal with this rather a complicated and toilsome dispatch problem. In Part I of the two-part paper, a comprehensive review or a survey of PSO and its modified versions (involve alterations in the basic structure of PSO) to resolve the constrained ED problem is presented. Part II covers purely the survey of hybrid forms of PSO (hybridization of PSO with other optimization techniques) to tackle the ED problem. The survey is presented in such a way that readers may understand how PSO can be made computationally more efficient.

Although particle swarm optimization (PSO) in its standard form performs extremely well for less complicated convex optimization problems involving reduced search space, it fails in finding global optimal solutions for more complicated nonconvex optimization problems with multiminima functions, thus exploring the promising search space less efficiently to ensure solution with superior quality. Guaranteeing the location of the global optimum through PSO becomes strenuous. The inherited premature convergence problem of PSO becomes more prominent while handling, especially the complex nonconvex problems. However, PSO has the ability to hybrid with other optimization techniques to ensure optimal global solution, better convergence characteristics, computational efficiency, and so on, while dealing with complex nonconvex problems. After presenting a detailed survey of the variants of PSO (involving variations in the basic structure of PSO) in part I, part II of this paper now comprehensively details all the hybrid forms (purely) of PSO applied to a constrained economic dispatch problem. How PSO overcomes its premature convergence problem while hybridizing with other optimization techniques is well-highlighted.

Machine learning (ML) based bearing fault detection is an emerging application of Artificial Intelligence (AI) that has proven its utility in effectively classifying various faults for timely measures. There are myriad studies dedicated to the effective classification of bearing faults under different conditions and experimental settings. In this study, we proposed a weighted voting ensemble (WVE) of three low-computation custom-designed convolutional neural networks (CNNs) to classify bearing faults at 48KHz. Some of the recent studies have exploited 1-d time-series signals and time-frequency based 2-d transformations for bearing fault classification. However, 1-d signals lack contextual information and higher-dimensional interpretations whereas time-frequency based transformations provide a more appropriate, visually perceivable and explainable representation of the time and frequency changes. Therefore in this study, a scalogram based representation of the signals is leveraged for classification using the CNN. Furthermore, the class imbalance is a significant challenge that affects the modelling behavior and possibly create biases. This study provides a novel density and distance hybrid over-sampling approach namely Density-AwareSMOTE(DA-SMOTE) built upon theSMOTE methodology for a more refined representation of synthetic samples within the minority class distribution. The experimentation procedures were carried out before and after the oversampling and it was observed that the balanced dataset acquired much better accuracy then the imbalanced dataset. This is evident by the fact that the highest validation accuracy for the proposed ensemble method (WVCNN) reached at 0-HP and 1-HP reached 99.28% and 99.13% while for the over-sampled dataset the accuracy soared to 99.71% and 99.87% for 0 and 1-HP respectively. The performance was evaluated for other metrics apart from the accuracy to assess the model’s performance in terms of chance occurrences and the class wise performance.

The paper presents a modified hybrid particle swarm optimization with bat algorithm parameter inspired acceleration coefficients (MHPSO-BAAC) without and with the constriction factor to find the optimal solution of the economic dispatch problems (EDPs) incorporating conventional as well as hybrid and renewable energy sources (RESs) based plants. The algorithm is designed by modifying the recently presented hybrid PSO and BA (HPSOBA) algorithm applied for the achievement of the optimal solution of the EDPs. The modified algorithm is implemented to solve EDPs of all RESs-based power systems for three scenarios, without constraints, with time-varying demand, and with the consideration of regional load sharing dispatch (RLSD). The performance of the algorithm is also verified through the implementation of various combinations of hybrid as well as thermal power plants (TPPs). The case of TPPs consists of three different scenarios: 1) a small-scale system with constraints like ramp-rate limits (RRLs), prohibited operating zones (POZs), and power losses; 2) a medium-scale power system with consideration of emission-economic dispatch (EED); 3) a large-scale power system with valve-point loading (VPL) effect. The results of the designed MHPSO-BAAC algorithm are compared with the various metaheuristic algorithms available in the literature and the comparative analysis shows the superior performance of the developed algorithm in terms of fuel cost reduction, fast convergence, and computational time.